Computers submit requests of different types to a server. The response times of the server to the submitted requests is measured. Then, the average response times of the server is predicted based on the number and types of requests and the measured response times.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A computer implemented method for measuring and predicting a performance of a server comprising the computer implemented steps of: submitting a first predetermined number of requests of a first predetermined number of different types of requests to a server; measuring first response times of the server to the submitted first predetermined number of requests; calculating a first set of average coefficients using a model based on the measured first response times; predicting first average response times of the server using the model based on the first predetermined number of requests, the first predetermined number of different types of requests, and the first set of average coefficients; and generating a performance model of the server based on the measured first response times and the predicted first average response times.
2. The method of claim 1 , further comprising, determining the a capacity of the server based on the first predetermined number of requests and the predicted first average response times.
3. The method of claim 1 , wherein the server comprises a Web server.
4. The method of claim 1 , wherein the first predetermined number of requests comprise e-commerce requests.
5. The method of claim 1 , wherein the first predetermined numbers of different types of requests are programmable parameters of a program implemented by the computer.
6. The method of claim 1 , wherein the first predetermined number of different types of requests comprise at least one of a price range, a keyword, and a plurality of keywords.
7. The method of claim 1 , further comprising, generating a matrix to set the first predetermined number of requests to submit to the server.
8. The method of claim 1 , further comprising, using a generalized linear model to calculate the first set of average coefficients and to predict the first average response times.
9. The method of claim 1 , further comprising, submitting a second predetermined number of requests of a second predetermined number of different types of requests to the server; measuring second response times of the server to the submitted second predetermined number of requests; calculating a second set of average coefficients using a model based on the measured second response times; predicting second average response times of the server using the model based on the second predetermined number of requests, the second predetermined number of different types of requests and the second set of average coefficients; and validating the performance model of the server based on the measured second response times and the predicted second average response times.
10. The method of claim 9 , wherein the second predetermined number of different types of requests is a random number.
11. The method of claim 9 , further comprising, using a generalized linear model to calculate the second set of average coefficients and to predict the second average response times.
12. A machine-readable medium comprising encoded information, which when read by a machine causes the acts of: submitting a first predetermined number of requests of a first predetermined number of different types of requests to a server; measuring first response times of the server to the submitted first predetermined number of requests; calculating a first set of average coefficients using a model based on the measured first response times; predicting first average response times of the server using the model based on the first predetermined number of requests, the first predetermined number of different types of requests, and the first set of average coefficients; and generating a performance model of the server based on the measured first response times and the predicted first average response times.
13. The machine-readable medium of claim 12 , further comprising, determining the a capacity of the server based on the first predetermined number of requests and the predicted first average response times.
14. The machine-readable medium of claim 12 , wherein the server comprises a Web server.
15. The machine-readable medium of claim 12 , wherein the first predetermined number requests comprise e-commerce requests.
16. The machine-readable medium of claim 12 , wherein the first predetermined numbers of different types of requests are programmable parameters of a program implemented by the computer.
17. The machine-readable medium of claim 12 , wherein the first predetermined number of different types of requests comprise at least one of a price range, a keyword, and a plurality of keywords.
18. The machine-readable medium of claim 12 , further comprising, generating a matrix to set the first predetermined number of requests to submit to the server.
19. The machine-readable medium of claim 12 , further comprising, using a generalized linear model to calculate the first set of average coefficients and to predict the first average response times.
20. The machine-readable medium of claim 12 , further comprising, submitting a second predetermined number of requests of a second predetermined number of different types of requests to the server; measuring second response times of the server to the submitted second predetermined number of requests; calculating a second set of average coefficients using a model based on the measured second response times; predicting second average response times of the server using the model based on the second predetermined number of requests, the second predetermined number of different types of requests and the second set of average coefficients; and validating the performance model of the server based on the measured second response times and the predicted second average response times.
21. The machine-readable medium of claim 20 , wherein the second predetermined number of different types of requests is a random number.
22. A system comprising: a server; and a plurality of computers adapted to communicate with the server, each of the computers includes at least one agent, a first agent adapted to submit a first predetermined number of requests of a first predetermined number of different types of requests to the server, a second agent adapted to measure first response times of the server to the submitted first predetermined number of requests, and one of the computers adapted to calculate a first set of average coefficients and to predict first average response times of the server using a model based on the first predetermined number of requests, the first predetermined number of different types of requests, and the first set of average coefficients, and generate a performance model of the server based on the measured first response times and the predicted first average response times.
23. The system of claim 22 , wherein one of the computers is adapted to determine a capacity of the server based on the first predetermined number of requests and the predicted first average response times.
24. The system of claim 22 , wherein the server comprises a Web server.
25. The system of claim 22 , wherein the first predetermined number of requests comprise e-commerce requests.
26. The system of claim 22 , wherein the first predetermined numbers of different types of requests are programmable parameters of a program implemented by the computer.
27. The system of claim 22 , wherein the first predetermined number of different types of requests comprise at least one of a price range, a keyword, and a plurality of keywords.
28. The system of claim 22 , wherein the first agents is adapted to generate a matrix to set the first predetermined number of requests to submit to the server.
29. The system of claim 22 , wherein one of the computers is adapted to use a generalized linear model to calculate the first set of average coefficients and to predict the first average response times.
30. The system of claim 22 , further comprising, the first agent adapted to submit a second predetermined number of requests of a second predetermined number of different types of requests to the server, the second agent adapted to measure second response times of the server to the submitted second predetermined number of requests, and one of the computers adapted to calculate a second set of average coefficients and to predict second average response times of the server using a model based on the second predetermined number of requests, the second predetermined number of different types of requests and the second set of average coefficients, and to validate the performance model of the server based on the measured second response times and the predicted second average response times.
31. The system of claim 30 , wherein the second predetermined number of different types of requests is a random number.
32. The method of claim 30 , further comprising, using a generalized linear model to calculate the second set of average coefficients and to predict the second average response times.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
June 27, 2000
January 27, 2004
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.